Viewer helper (hidden): finds objects on one frame (text, points or boxes) for the Mask + Matting viewer and writes one mask per object. Not meant to be added…

Experimental nodes! This is a production suite for ComfyUI — SAM2.1/SAM3 segmentation, alpha matting, inpaint crop/stitch, VFX tools (EXR I/O, LUTs, render passes), video mask propagation, temporal anchors, VAE merging, spline editors, and auto-versioned output.

ComfyUI-CustomNodePacks

image

frame

model

text

points

boxes

max_side

Viewer helper (hidden): finds objects on one frame (text, points or boxes) for the Mask + Matting viewer and writes one mask per object. Not meant to be added by hand.

Name	Type	Default	Description
image	IMAGE		The plate.
frame	INT	00–1000000	Frame to look at.
model	COMBO	MISSING: sam3.1_multiplex_fp16.safetensors	SAM checkpoint for Find and clicks, strongest first (SAM 3.1 Multiplex > 3.1 > 3), from models/sam3.1 and models/sam3.
textopt	STRING		What to find, comma-separated (person, dog).
pointsopt	STRING		Clicks: [{"x":0.4,"y":0.5,"label":1}] in 0..1.
boxesopt	STRING		Boxes: [[x0,y0,x1,y1]] in 0..1.
max_sideopt	INT	96064–2048	—

Viewer helper: Detect

Inputs (7)

Outputs (0)